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

  • synaesthetic - Sunday, March 20, 2011 - link

    Touchscreens are the very antithesis of good ergonomics. Unless haptic feedback can defy physics or we get some deformable/flexible screens, devices with actual buttons will always be superior.

    The human brain simply reacts better to physically pushing a button. Touchscreens have horrible ergonomics--a tiny bit of vibration is not really much haptic feedback. It feels like a lot to us (and it certainly helps me on my phone) but it only feels like that beccause a touchscreen is so far away from any semblance of "natural use."

    Touchscreens should be used when they are REQUIRED--such as on smartphones, where the number of controls, commands and options far outstrip the physical size of the device and the physical space to place buttons.

    I don't think tablets will ever stop being a toy.
    Reply
  • stephenbrooks - Saturday, March 19, 2011 - link

    Page 2, final picture. The iPad 2 is on the BOTTOM not the top there. Reply
  • Anand Lal Shimpi - Saturday, March 19, 2011 - link

    Fixed! Thanks :) Reply
  • Omid.M - Saturday, March 19, 2011 - link

    "There's also the idea of synergy among devices. Even if you play within the Apple universe and own a Mac, an iPhone and an iPad, there's no magical way of sharing data and applications between them. I should be able to work on my Mac, step away and have my apps/data come with me. Your best bet is something like Dropbox but that's no where near the type of cohesive solution I'm talking about. Think HP's webOS touch-to-share but on steroids and you're on the right track."

    Anand/Brian/Vivek:

    I'm sure that's what Apple is planning with NFC-enabled iOS devices, but then wouldn't that require a saved state to be stored in the cloud and then re-downloaded on demand on the next device used? I would imagine that "lag" in the UX would be a problem. How long would you feasibly have to wait for stuff to download the first time you sit down with a new device (new as in rotation) ?

    Also, would this be limited to stock-Apple stuff only? It would be a bear for Apple to save the state of arbitrary 3rd party software from one device to the next (assuming both devices have the client installed). Right?

    Next...

    "So if you're actually torn between the iPad 2 and the Xoom my best advice is to wait. Apple needs to update iOS in a major way and Honeycomb needs a hardware update. Whichever gets it right first should get your money."

    This is really the money statement of the review. I think Android tab makers need to NOT simply look at the iPad 2 to figure out their next move, but to pave their own path, not for the path to be a RESPONSE to the competition. The Xoom should have higher quality display for sure, and Honeycomb needs faster incremental updates. I really liked it but it just lacks so much in terms of functionality and compatibility, at least if we're considering it for productivity.

    None of the tabs on the market right now are really meant for editing/creating content--even if you're able to with a handful of apps--but simply consuming existing content (iTunes music streaming, sharing videos, social networking--and I think that's the biggest issue with tablet to replace netbooks or become devices taken seriously.

    Please, please cover the WebOS tablet when it comes out.

    Thanks for the review, guys. Great work. The technical section on glass, for instance, is one reason with AT does the best reviews.

    Worth the read. Will tweet for others to check it out!

    -Omid
    Reply
  • clb - Monday, April 04, 2011 - link

    I agree on both, but the point on #1 is missed. It is not the need for the cloud on NFC, but the fact that you cannot actually sync the device:

    >I should be able to work on my Mac, step away and have my apps/data come with me.

    Even if you are going from a Mac to the iPad (1 or 2), there is no sync feature that covers everything. A note created on the iPad has to be emailed to your Mac; Apple will not let you read a note created on the iPad on a Mac unless you email it to yourself! And there is no way to get a note into the Likewise, using DropBox is great, but now files have to be loaded up, then you must reconnect, then load down. You cannot simply have the Mac send to the iPad or vice versa.

    This is because unlike the early iPods, the iPhones and iPads do not allow the user to move files. Early iPods could be treated as FireWire drives. Not the iOs devices. Everything must go through iTunes or via the cloud (i.e., third-party sites). If I'm at a beach house with no cloud connection, and want to move content from my PC/Mac to my iPad, I'm SOL in many cases.

    This is bad.
    Reply
  • Adam Chew - Saturday, March 19, 2011 - link

    Judging from your review of the iPad, its competitors will stand no chance of ever gaining traction in everyday use.

    So get a Macbook Air.....LOL

    The problem is the everyday user is not a tech blog blogger, the iPad is ideal for consumption of everything of the net and not like some tech blogger who needs to blog unnecessarily with a laptop when an iPad is at hand.
    Reply
  • nickdoc - Sunday, March 20, 2011 - link

    Loved your contribution! The geek talk was getting really boring and repetitive. Hello! Normal people have needs, too. This is what the reviewers often forget. Not everyone needs to create content to be consumed by other creators of mostly the same content. Lol! Reply
  • stephenbrooks - Saturday, March 19, 2011 - link

    OK, why where you joining *two iPads* together with magnets and buying a "smart vase" from Apple? :D

    "The iPad aligns and attaches to the body of the iPad 2 using six magnets along its side that line up with a similar set of magnets on the device. When I acquired the smart vase at launch, I [...]"
    Reply
  • Anand Lal Shimpi - Saturday, March 19, 2011 - link

    Fixed again :) Reply
  • tipoo - Saturday, March 19, 2011 - link

    How the f does it work? Reply

Log in

Don't have an account? Sign up now