The GPU: Apple's Gift to Game Developers

The GPU side of the A5 is really what's most exciting. As we mentioned in our iPad 2 GPU Performance analysis, the A5 includes a dual-core PowerVR SGX 543 - also known as the SGX 543MP2. In our earlier article we showed the SGX 543MP2 easily beating both an iPad 1 and the Tegra 2 based Motorola Xoom.

To understand why the SGX 543MP2 has such a performance advantage we need to first remember that NVIDIA's Tegra 2 is nearly a year late. NVIDIA's first competitive ultra mobile GPU was supposed to be shipping in products in the first half of 2010, instead it found itself shipping in 2011. While NVIDIA is good at designing GPUs, it's not good enough that it can release a product and maintain a two year performance advantage over the competition. Let's look at the architecture, shall we?

NVIDIA's Tegra 2 features a DirectX 9-class GPU. NVIDIA used to call it the GeForce ULP (Ultra Low Power) but now it's just GeForce. As a DX9 class GPU we're dealing with a conventional, non-unified shader architecture. While all OpenGL ES 2.0 GPUs can execute pixel and vertex shader instructions, the GeForce in Tegra 2 runs pixel and vertex shaders on separate groups of hardware.

NVIDIA calls each pixel and vertex shader ALU a core. The Tegra 2 has four pixel shader cores and four vertex shader cores. The four pixel shader ALUs make up a single Vec4 and the same goes for the four vertex shader ALUs. NVIDIA wouldn't elaborate on what limitations exist when dispatching operations to the cores. All pixel shader operations happen at 20-bits per component precision while all vertex shader operations happen at 32-bits per component.

Each core is capable of executing one multiply+add (MAD) operation per clock. Do the math and that works out to be a peak rate of 8 MADs per clock for the entire GPU. The maximum operating frequency for the Tegra 2 GeForce GPU is 300MHz, however device vendors may run the GPU at a lower frequency to save on power. At 300MHz this works out to be 4.8 GFLOPS (counting a MAD as two FLOPs).

Imagination Technologies' PowerVR SGX 543MP2 is fundamentally a bigger GPU than the GeForce in NVIDIA's Tegra 2. Let's go through the math.

The SGX 543 features four USSE2 pipes. This is a unified shader architecture so both vertex and pixel shader code runs on the same set of hardware. The benefit of this approach is you get better performance in peaky situations where you're running a lot of vertex or pixel shader code and not a balance that's perfectly tailored to your architecture. The Tegra 2 will only run at peak efficiency if it encounters a mix of 50% vertex and 50% pixel shader code. The PowerVR SGX series will never have any of its execution pipes idle regardless of the instruction mix.

Each USSE2 pipe has a 4-wide vector ALU capable of cranking out 4 MADs per clock. Two of these pipes is enough to equal the peak throughput of what NVIDIA built in Tegra 2, but the PowerVR SGX 543 has four of them. As for the MP2? Go ahead and double that number again. The SGX 543MP2 is simply two 543s placed next to one another.

All of this works out to be 16 MADs per clock for the SGX 543 and 32 MADs per clock for the SGX 543MP2. At 200MHz that's 12.8GFLOPS and at 250MHz we're talking about 16 GFLOPS.

Mobile SoC GPU Comparison
  PowerVR SGX 530 PowerVR SGX 535 PowerVR SGX 540 PowerVR SGX 543 PowerVR SGX 543MP2 GeForce ULP Kal-El GeForce
SIMD Name USSE USSE USSE USSE2 USSE2 Core Core
# of SIMDs 2 2 4 4 8 8 12
MADs per SIMD 2 2 2 4 4 1 ?
Total MADs 4 4 8 16 32 8 ?
GFLOPS @ 200MHz 1.6 GFLOPS 1.6 GFLOPS 3.2 GFLOPS 6.4 GFLOPS 12.8 GFLOPS 3.2 GFLOPS ?
GFLOPS @ 300MHz 2.4 GFLOPS 2.4 GFLOPS 4.8 GFLOPS 9.6 GFLOPS 19.2 GFLOPS 4.8 GFLOPS ?

At its lowest expected clock speed, the 543MP2 already has over twice the compute power of the Tegra 2's GPU at its highest operating frequency. Take into account the fact that the A5 likely has more memory bandwidth than Tegra 2 and the SGX 543MP2 is a tile based architecture with lower bandwidth requirements and the performance numbers we talked about last time shouldn't be all that surprising.

The real competition for the SGX 543MP2 will be NVIDIA's Kal-El. That part is expected to ship on time and will feature a boost in core count: from 8 to 12. The ratio of pixel to vertex shader cores is not known at this point but I'm guessing it won't be balanced anymore. NVIDIA is promising 3x the GPU performance out of Kal-El so I suspect that we'll see an increase in throughput per core.

GPU Performance

Taken from our iPad 2 GPU Performance Preview:

As always we turn to GLBenchmark 2.0, a benchmark crafted by a bunch of developers who either have or had experience doing development work for some of the big dev houses in the industry. We'll start with some of the synthetics.

Over the course of PC gaming evolution we noticed a significant increase in geometry complexity. We'll likely see a similar evolution with games in the ultra mobile space, and as a result this next round of ultra mobile GPUs will seriously ramp up geometry performance.

Here we look at two different geometry tests amounting to the (almost) best and worst case triangle throughput measured by GLBenchmark 2.0. First we have the best case scenario - a textured triangle:

Geometry Throughput - Textured Triangle Test

The original iPad could manage 8.7 million triangles per second in this test. The iPad 2? 29 million. An increase of over 3x. Developers with existing titles on the iPad could conceivably triple geometry complexity with no impact on performance on the iPad 2.

Now for the more complex case - a fragment lit triangle test:

Geometry Throughput - Fragment Lit Triangle Test

The performance gap widens. While the PowerVR SGX 535 in the A4 could barely break 4 million triangles per second in this test, the PowerVR SGX 543MP2 in the A5 manages just under 20 million. There's just no competition here.

I mentioned an improvement in texturing performance earlier. The GLBenchmark texture fetch test puts numbers to that statement:

Fill Rate - Texture Fetch

We're talking about nearly a 5x increase in texture fetch performance. This has to be due to more than an increase in the amount of texturing hardware. An improvement in throughput? Increase in memory bandwidth? It's tough to say without knowing more at this point.

Apple iPad vs. iPad 2
  Apple iPad (PowerVR SGX 535) Apple iPad 2 (PowerVR SGX 543MP2)
Array test - uniform array access
3412.4 kVertex/s
3864.0 kVertex/s
Branching test - balanced
2002.2 kShaders/s
11412.4 kShaders/s
Branching test - fragment weighted
5784.3 kFragments/s
22402.6kFragments/s
Branching test - vertex weighted
3905.9 kVertex/s
3870.6 kVertex/s
Common test - balanced
1025.3 kShaders/s
4092.5 kShaders/s
Common test - fragment weighted
1603.7 kFragments/s
3708.2 kFragments/s
Common test - vertex weighted
1516.6 kVertex/s
3714.0 kVertex/s
Geometric test - balanced
1276.2 kShaders/s
6238.4 kShaders/s
Geometric test - fragment weighted
2000.6 kFragments/s
6382.0 kFragments/s
Geometric test - vertex weighted
1921.5 kVertex/s
3780.9 kVertex/s
Exponential test - balanced
2013.2 kShaders/s
11758.0 kShaders/s
Exponential test - fragment weighted
3632.3 kFragments/s
11151.8 kFragments/s
Exponential test - vertex weighted
3118.1 kVertex/s
3634.1 kVertex/s
Fill test - texture fetch
179116.2 kTexels/s
890077.6 kTexels/s
For loop test - balanced
1295.1 kShaders/s
3719.1 kShaders/s
For loop test - fragment weighted
1777.3 kFragments/s
6182.8 kFragments/s
For loop test - vertex weighted
1418.3 kVertex/s
3813.5 kVertex/s
Triangle test - textured
8691.5 kTriangles/s
29019.9 kTriangles/s
Triangle test - textured, fragment lit
4084.9 kTriangles/s
19695.8 kTriangles/s
Triangle test - textured, vertex lit
6912.4 kTriangles/s
20907.1 kTriangles/s
Triangle test - white
9621.7 kTriangles/s
29771.1 kTriangles/s
Trigonometric test - balanced
1292.6 kShaders/s
3249.9 kShaders/s
Trigonometric test - fragment weighted
1103.9 kFragments/s
3502.5 kFragments/s
Trigonometric test - vertex weighted
1018.8 kVertex/s
3091.7 kVertex/s
Swapbuffer Speed
600
599

Enough with the synthetics - how much of an improvement does all of this yield in the actual GLBenchmark 2.0 game tests? Oh it's big.

GLBenchmark 2.0 Egypt

Without AA, the Egypt test runs at 5.4x the frame rate of the original iPad. It's even 3.7x the speed of the Tegra 2 in the Xoom running at 1280 x 800 (granted that's an iOS vs. Android comparison as well).

GLBenchmark 2.0 Egypt - FSAA

With AA enabled the iPad 2 advantage grows to 7x. In a game with the complexity of the Egypt test the original iPad wouldn't be remotely playable while the iPad 2 could run it smoothly.

The Pro test is a little more reasonable, showing a 3 - 4x increase in performance compared to the original iPad:

GLBenchmark 2.0 PRO

GLBenchmark 2.0 PRO - FSAA

While we weren't able to reach the 9x figure claimed by Apple (I'm not sure that you'll ever see 9x running real game code), a range of 3 - 7x in GLBenchmark 2.0 is more reasonable. In practice I'd expect something less than 5x but that's nothing to complain about.

The Right SoC at the Right Time: Apple's A5 Battery Life
POST A COMMENT

189 Comments

View All Comments

  • Mishera - Wednesday, March 23, 2011 - link

    An and you made an excellent point when you said that tablets don't seem on a path towards perfection.  Right now IPads are somewhat of a novelty.  They're kind of like that thing you see at a museum as a child that make you go "wow" or a concept at a convention that's not fully realized.  The problem is people seem content with the device as it is because it's Apple, and companies are trying the "square in circle" method to put it in schools, businesses, etc.

    Thats what really bothers me. Apple pretty much marches on it's own beat, consumers eat up what they release, and companies desperately try to run behind them and release something with better specs, never questioning if there is a better direction.  As a consumer device it's excellent, its just there are so many more directions tablets can go.  I would almost would say that Microsoft had a better idea of what a tablet should be with their umpc line, except they could never get the ui right, and now it seems like their hardware endeavors are over for so I wonder who could really bring a better concept to market.  To make tablets work it's going to take on os and a hardware so far android can't do it, microsoft won't to it and hp is still a question mark so we just have to be content with whatever apple gives us.  
    Reply
  • Zink - Sunday, March 27, 2011 - link

    Here's a very surprising video showing the flexibility of the glass used in the screen.
    http://www.youtube.com/watch?feature=player_embedd...
    Reply
  • JustinB - Monday, March 28, 2011 - link

    While OEMs are racing to create a competitor to the iPad, it seems like commenters on sites like this are trying to create a competitor to the Reality Distortion Field... Reply
  • NetJunky - Tuesday, April 19, 2011 - link

    Actually Dropbox has its own lack of security. So I wouldn't say, that this is a best example of data sharing via web. Reply
  • Bronx 6 - Tuesday, June 28, 2011 - link

    Apple had touch first congrats.They can keep there not so tech ridiculously rich ppl who buy lesser powerful or frivolous shoppers.xoom is to much with not enough (like ipad) on board no dongle needed ports/hdmi/usb/micro usb like acer.i bought an ipad2 as my first owned apple product just so I could show everyone whata piece crap it is and then return it to the store.The things I get off android apps are sooooooo much better because they arent being ran by the Nazi's (apple).,i like not having to waste money on anything app wise,movie(better than anything I could dream for) and of course free absolutely FREE music mp3s.now I even get artwork on them and they appear just as if I bought them.The music mp3 apps even (some) even include music charts so you know what's new and hot.i dont need cable tv,satelite,nadda I get thousands of channels free from apps which use flash and lemme tell flash is the key to the future and present.i love how developers make the good apps ipad has for honeycomb tabs(splashtop hd remote desktop)-myfav allows me to use all pcs as if I was on it even whem im in another state.the resolution is amazing also the many keyboards u can get-new swype is surreal should be stock on all tabs.tried to ruin acertab with viruses it wont phase it amazing alone.i so love the apps on droid they are made by ppl wno arent like the government and honeycomb keeps getting better asnow 3.1 is so muchbetter and its free.the power.of these tabs are like two ipads and the cameras on ipad2 is patheic like an old boostmobile vga cam.mine has the same quality cameras as iphone4 has another + acer has the best tab for the buck they have a functual full usb port and it connects alot.of useful things like keyboard,flashdrives,ch arging capabilites.i had bought one accessery a case stand that's it had hdmi cords already.the ipad I bought over 8 seperate things totally a money hungry company who designs product too keep you buying shit week after week.itunes is just plain retarded.i get the sameshit they do for free easier than a pc.wide open is free like usa is supposedly.if ur reading this and have a tablet download swype beta for honeycomb.It takes the basic stock keyboard but adds stuff u will love even if you dont swype u type better than the stock more like a real one.i bought 2apps in 2YRS yet ive had more than I can think of.i spent $8 total.i have sold more of these to anyone I show and teach.my old mother has one and now wont use her win7 pc's only thru the tablet-thats including me fixing her old pcs accross the country in california all from my badass acer tablet.apple should stick to ipods.droid tabs are diffently ipad.killers.i hope ppl enjoy wasting their money basically getting raped.so dumb ppl stay apple,smart ppl sick of paying for things that we shouldnt and having the ability to do all n then some on tablets enjoy.ps these flash modified apps on droids I cant praise the quality they look during playback is wow.ive watched more hdtv thru this than I have in years with my hdtv sets pretty crazy,so is the gaming similar to xbox360.buy an galaxy tab first then return it for an acer so you can appreciate getting more for less.send me the difference for enlighting u on values of better things.then again the world is more than 50% ignorant and very rude to ones who help them.take it as grain of salt Reply
  • rampantarmadillo - Thursday, August 18, 2011 - link

    I recommend that you learn to seperate vertex and fragment perf, this would demonstrate you aren't clowns. Reply
  • powchie - Saturday, December 10, 2011 - link

    anand, brian,
    what's that workflow that the iPad cannot fit in?
    Reply
  • ChaoticCupcake - Tuesday, December 27, 2011 - link

    Any word on whether or not a camera can be attached and used as a webcam for FaceTime, Skype, etc.? Reply
  • omkarphatak - Tuesday, February 28, 2012 - link

    Find out why choosing an iPad 2 over a laptop makes no sense... http://www.buzzle.com/articles/which-is-better-ipa... Reply

Log in

Don't have an account? Sign up now