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

232 Comments

View All Comments

  • antef - Wednesday, March 28, 2012 - link

    Yes it's nice, no one will argue that. But I don't see it as the huge advancement the authors indicate. Using it in the store it seemed fine, but honestly just walking right up to it, I wasn't even sure if I was using the new or old iPad. I had to go over to the iPad 2 to recognize the difference. And even then, after being back at the new iPad for a couple minutes, I completely forgot about it. If you are looking for pixels, sure, you'll notice. If you're just using your device and thinking about other things, probably not so much. Reply
  • PeteH - Wednesday, March 28, 2012 - link

    Eh, I think it depends on what application you use the iPad for. Web browsing and Tweeting? You're probably right, you wouldn't notice the difference in displays. But if you use it to view images I could see it being a big deal. Reply
  • zorxd - Wednesday, March 28, 2012 - link

    I am pretty sure extra resolution is more noticeable when reading text than when looking at images Reply
  • PeteH - Wednesday, March 28, 2012 - link

    I didn't mean "notice" as in you couldn't tell the difference, just that the difference wouldn't be something that you would constantly be aware of if you were simply web browsing.

    If you were reading an e-book? Absolutely, but if that's your only use case I'd get a Kindle and save the money.

    Regularly viewing quality images is something that can't be done on an e-ink reader, but for which the improved display would make a huge difference.
    Reply
  • Sabresiberian - Thursday, March 29, 2012 - link

    I would say this is a perfect example of why it's better to use "I"" statements than say "YOU won't notice, YOU won't care, there isn't that much difference" - those kinds of statements. "I didn't notice much of a difference, it wasn't a big change in MY experience. . .)

    Displays can very very personal in experience, and things that bug the heck out of me may not be a problem to someone else. For example, a pixel pitch of around .270mm is just too big for me, in a monitor, and it bugs me. Always.

    Frame rates are a good example of something I'm not consciously aware of all the time, but I can sure tell the difference on some level, and some displays are more effected than others. There are extra factors in LCD screens that can make the problem worse for some of us - others don't notice so much, or it's just not a problem for them.

    One thing I believe, is that as more people use really better screens, they'll understand more why some of us call for them every chance we get.

    ;)
    Reply
  • darkcrayon - Wednesday, March 28, 2012 - link

    I can *immediately* notice the difference in web browsing, which is primarily focused on reading text... Reply
  • tipoo - Wednesday, March 28, 2012 - link

    I found it a noticeable difference, just not neuron melting like some reviews led me to think. For 100 or more less I'd still be plenty happy with an iPad 2, especially given the CPU and battery life performance are about the same. Reply
  • MobiusStrip - Thursday, March 29, 2012 - link

    Unfortunately the iPad 2's camera is a disgrace. It should've had the iPhone 4 camera, which was already out by that time. Reply
  • repoman27 - Thursday, March 29, 2012 - link

    The iPad 2 was also thinner than the iPhone 4. Now that it is the same width, it has the same camera. It's not really Apple's style to add thickness to a device just to support one feature that isn't heavily used anyway (tablets are not a very good form factor for a camera.) Reply
  • zanon - Wednesday, March 28, 2012 - link

    Human vision varies significantly from person to person, as do use patterns for machines. Someone who is more near sighted or simply has better vision in general, and/or uses their system at a closer distance, may see a truly dramatic change. To take my personal example, I have excellent color vision and am also near sighted, and tend to hold my devices relatively close (or use glasses at my machine). I can see the pixels on the iPhone 4 screens (326 ppi) if I focus a bit, and for the older screens (or old iPads) they're massively pixelated to me (not that that made them useless). The High DPI screens are a night/day difference personally, making all types of reading in particular (be it on a terminal session, the web, PDF manuals, ebooks, or whatever) massively more functional (and everything else more beautiful).

    But that's just me, and is that awesome? No, it's kind of meh, I'd love it if I didn't need glasses to use my desktop without being hunched over the keyboard to drive. But understand that you'll see raves about the screen that are completely justified, just not for you. 20/20 vision puts the critical distance around 13" I think, but in the end everyone will need to take a look for themselves.
    Reply

Log in

Don't have an account? Sign up now