Apple iPad 2 GPU Performance Explored: PowerVR SGX543MP2 Benchmarked
by Anand Lal Shimpi on March 12, 2011 3:04 PM EST- Posted in
- Smartphones
- Apple
- iPad
- GLBenchmark
- iPad 2
- Mobile
- Tablets
GLBenchmark 2.0
GLBenchmark 2.0—as its name implies—tests OpenGL ES 2.0 performance on compatible devices. The suite includes two long benchmarking scenarios with a demanding combination of OpenGL ES 2.0 effects - texture based and direct lighting, bump, environment, and radiance mapping, soft shadows, vertex shader based skinning, level of detail support, multi-pass deferred rendering, noise textures, and ETC1 texture compression.
GLBenchmark 2.0 is the best example of an even remotely current 3D game running on this class of hardware—and even then this is a stretch. If you want an idea of how the PowerVR SGX 543MP2 stacks up to the competition however, GLBenchmark 2.0 is probably going to be our best bet (at least until we get Epic to finally release an Unreal Engine benchmark).
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).
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:
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. We'll be doing power analysis over the weekend so expect more detail in our full review.
Putting the PowerVR SGX 543MP2 to Use: Infinity Blade
As we pointed out in our iPad 2 Preview, at least one developer already picked up on the amount of extra GPU horsepower in the new iPad 2. Epic put out an updated version of Infinity Blade with support for the iPad 2. Run it on an iPad and you'll get the same old Infinity Blade, but run it on an iPad 2 and you'll get more detail, higher resolution textures and anti-aliasing.
Remember that iPad and iPhone devices are more closed than your PC. There's no adjusting detail settings or resolution, so the target frame rate is usually what's fixed. Developers are simply able to deliver a better looking experience at roughly the same frame rate with upgraded hardware. In the case of Infinity Blade, load times are reduced thanks to the Cortex A9 CPU cores and there is some improvement in frame rate but the biggest impact comes from the improved visuals.
Below is the comparison beween Infinity Blade on the iPad and iPad 2 we ran in this morning's preview:
Mouse over to see Infinity Blade on the iPad 2
There's far more detail in the character models as well as the environment. Lighting looks improved and the AA is definitely appreciated.
Mouse over to see Infinity Blade on the iPad 2
The gallery below has a bunch of side by side shots showing the improvements made to Infinity Blade for the iPad 2 vs. what you get when you run the game on a first generation iPad.
To Be Concluded...
We're still hard at work on our full iPad 2 review. We've got no less than four units running through battery life tests right now and there's still more to talk about in the review. We'll keep you posted, thanks for reading!
219 Comments
View All Comments
rish95 - Sunday, March 13, 2011 - link
This is wrong. The SGX543MP2 has 16 4-way ALUs. A single SGX 543 has 8 4-way ALUs. So make that 38.4 GFLOPS.somata - Sunday, March 13, 2011 - link
Where did you get that info? I'll admit I based my initial knowledge of the SGX543 on what I gleaned from the informed discussion on the Beyond3D forums along with Wikipedia. Any publicly avaialable info from Imagination Technologies seems to only be available in press releases, which don't go into too much detail. I did find this, however, which officially disputes your 16 ALUs claim:http://www.imgtec.com/News/Release/index.asp?NewsI...
"[...]Taking the already high-performance four-pipe POWERVR SGX543, and then scaling that performance up to between eight and 64 pipelines[...]"
After further reading, it appears that SGX535 actually contains just 2, 32-bit-wide shaders (4-way int8, 2-way in16, and just one fp32 ALU per pipe), based on this (GMA 500 uses PowerVR SGX535):
http://download.intel.com/design/chipsets/embedded...
The SGX543 doubles the number of shaders and improves on their capabilities (looks like 2-way fp32 ALUs based on "2x floating point" mentioned in the above PR), but I can't find any credible sources that explicitly discuss the exact changes. So it looks like my calculations may actually have been too high by a factor of two.
Juzcallmeneo - Sunday, March 13, 2011 - link
isn't that the GPU in the next PSP?tipoo - Sunday, March 13, 2011 - link
NGP = the next PSP, and yes, it will use the MP4B3an - Saturday, March 12, 2011 - link
"We've got no less than four units running through battery life tests right now"...You hardly ever do anything like this for other hardware.
And you already have two preview articles for this Apple junk in one day. Very obvious the favouritism here. You -even- seem to often spend more time taking better photo's of Apples products for your articles than you do with other products.
I'd ask if Apple was paying you or giving you free gear, like they have done with reviewers before, but i dont think Anand would atleast stoop that low.
rish95 - Saturday, March 12, 2011 - link
Maybe because Apple products are so hyped and popular? It's a known fact that the iPad 2 will outsell the Xoom by a huge margin, and more people would like to know about it.And clearly these benchamrks prove this isn't junk. It proves the Tegra 2 is junk.
ncb1010 - Saturday, March 12, 2011 - link
Well, the Tegra 2 actually beats the A5 in CPU tests. So it comes down to this:CPU or GPU...which do you prefer?
DeathChill - Saturday, March 12, 2011 - link
Just curious, where did you get this information? I haven't seen anything so I'm interested.rish95 - Saturday, March 12, 2011 - link
No it didn't? Both have dual core Cortex A9s clocked at 1 GHz with 1MB L2 cache. And if it did beat the iPad, it was probably Apple's strict as hell throttling system causing it.DigitalFreak - Saturday, March 12, 2011 - link
Go away little fanboy. The adults are having a conversation.