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

  • claytontullos - Saturday, March 19, 2011 - link

    http://technabob.com/blog/2011/03/18/ipad-2-refrig... kind of fun? Reply
  • vol7ron - Saturday, March 19, 2011 - link

    This just goes back to what I've said since the iPad was introduced. It'll be the +1 device that's best for laying around your house. This goes into my review as why it needs to hit the $200-250 price point.

    Sure it's a nice e-Reader and can entertain with some games and even allow for some production work, but it is still clunky and uncomfortable and to be efficient and productive you need the additional hardware, which are going to bring you in a nice laptop range anyhow.

    The 3GS is hitting the $50-100 price point w/ a 2 year contract, which I suggested a year ago. Personally, I still think that should be the price w/o the contract (to be available after-market for gifts/presents), but as long it's available at that point, that's where it needs to be.

    I still think the iPad needs to drop to that $200-250 point. It's the coffee table device, which people should consider having 2-3 spread-out in the home [ maybe one in the bathroom ;) ] - if only they could also self-sync wirelessly. I'm not too sure who buys the base model, but the specs alone would keep me from considering it and when you look at the higher spec'd models, it's not as justified when looking at laptops, or other eReaders.
    Reply
  • solipsism - Sunday, March 20, 2011 - link

    $200 to $250 for a newly released 10” Tablet with an IPS panel? WTF are you smoking? How can you have such an odd mental disconnect between writing that and then writing "The 3GS is hitting the $50-100 price point w/ a 2 year contract”? What part of 2-year contract aren’t you understanding? Do you not realize the carrier is paying Apple more than $200-250 for that 3GS, and you are paying the carrier a lot more than that over 2 years?

    Pray tell, how would this device be $200-250 when the competition with a 2 decade head start still hasn’t been able to compete on price?
    Reply
  • synaesthetic - Sunday, March 20, 2011 - link

    I don't get how they sell so many when they're so useless and clunky... and cost so much.

    Lot of hipsters I guess.
    Reply
  • michael2k - Sunday, March 20, 2011 - link

    The weight, battery life, and cost (altogether) are unparalleled in the computing world.

    Smartphones with similar performance characteristics have far smaller screens and lower battery life.

    PCs with similar battery life cost far more and weigh far more.

    PCs with similar weight (and still double at that) cost far more and have only fraction of the battery life.

    PCs with similar cost weigh far more and have drastically lower battery life.
    Reply
  • Meaker10 - Sunday, March 20, 2011 - link

    A dual core sandy bridge 13" device is going to be far more useful for work and far more powerful. Reply
  • michael2k - Sunday, March 20, 2011 - link

    Who said anything about work? For things like reading Anandtech it would be far heavier, bulkier, and with less battery life. Reply
  • bigboxes - Sunday, March 20, 2011 - link

    Just admit that it's a toy. The authors laid it out for you on how they prefer to use other devices instead of the iPad. It too bulky for portability and underpowered for any productivity tasks.

    So, you're telling me (and everyone else here) that you paid $500+ just to surf AnandTech on your couch? Just wondering.
    Reply
  • Stas - Monday, March 21, 2011 - link

    That's exactly why it cannot cost this much to be a reasonable buy. No, the following purchases are not reasonable: fa- sheep base, soccer moms that buy the latest gadget with most hype for their kids/husbands not even knowing wtf it does, or PR boost in form of including, again, the most hyped device with cars, hotel rooms, air travel, etc (3 categories right there probably account for 90% of all sales). I mean people that understand exactly what the device is, what it's not, and have a clear idea of how they are going to use it. And it doesn't matter how much it costs to make it, how advanced the hardware is, or how "revolutionary" the design is. Given the limited usability of a slim, touchscreen device, I think asking $600+ for one is ballsy. Reply
  • MScrip - Monday, March 21, 2011 - link

    -- "Given the limited usability of a slim, touchscreen device, I think asking $600+ for one is ballsy." --

    That's true about any tablet.

    As great as Honeycomb tablets are... they're still not gonna provide a true computing experience.

    A $600 laptop will always provide far more functionality than a $600 tablet...

    Yet... all these manufacturers are pumping out tablets at an alarming rate.

    Apple took the risk and added a new product to their lineup.

    If tablets were destined to fail... we wouldn't see Motorola, Samsung and even RIM jumping into the tablet game...
    Reply

Log in

Don't have an account? Sign up now