iPad 4 (Late 2012) Review
by Anand Lal Shimpi on December 6, 2012 4:40 PM ESTGPU Performance
The 4th generation iPad integrates a quad-core PowerVR SGX 554 (MP4). The 554MP4 doubles USSE2 count over the previous generation PowerVR SGX 543MP4 used in the iPad 3, while keeping ROP and TMU counts the same. The result is a pure doubling of peak theoretical shader performance:
| Mobile SoC GPU Comparison | |||||||||||
| PowerVR SGX 543 | PowerVR SGX 543MP2 | PowerVR SGX 543MP3 | PowerVR SGX 543MP4 | PowerVR SGX 554 | PowerVR SGX 554MP2 | PowerVR SGX 554MP4 | |||||
| Used In | - | iPad 2/mini | iPhone 5 | iPad 3 | - | - | iPad 4 | ||||
| SIMD Name | USSE2 | USSE2 | USSE2 | USSE2 | USSE2 | USSE2 | USSE2 | ||||
| # of SIMDs | 4 | 8 | 12 | 16 | 8 | 16 | 32 | ||||
| MADs per SIMD | 4 | 4 | 4 | 4 | 4 | 4 | 4 | ||||
| Total MADs | 16 | 32 | 48 | 64 | 32 | 64 | 128 | ||||
| GFLOPS @ 300MHz | 9.6 GFLOPS | 19.2 GFLOPS | 28.8 GFLOPS | 38.4 GFLOPS | 19.2 GFLOPS | 38.4 GFLOPS | 76.8 GFLOPS | ||||
The theoretical numbers validate Apple's "2x faster GPU" claims, but as always we'll turn to Kishonti's GLBenchmark to see how achievable that performance increase is.
We'll start out with the raw theoretical numbers beginning with fill rate:
The peak fill rate test shows a ~16% increase in performance over the previous generation 543MP4. Since there's no increase in number of TMUs we're seeing the results of a higher clocked GPU in the iPad 4's A6X.
There's a pretty hefty improvement in triangle throughput - we're seeing more than a 60% gain compared to the iPad 3.
At native resolution the fragment lit triangle texture test shows a big gain over the iPad 3 (~80%).
In both of the final triangle throughput tests the iPad 4 manages a 40 - 45% increase in performance over the iPad 3:
With the synthetics out of the way, we can look at simulated game performance using the Egypt HD and Egypt Classic benchmarks. Remember the on-screen tests are run at native resolution with v-sync enabled, while the offscreen tests are run at 1080p with v-sync disabled for an architectural apples-to-apples comparison.
Despite sub-2x gains in a lot of the synthetic tests, Egypt HD shows us what's possible in a simulated game: the new iPad is roughly twice the speed of the previous gen model when running at the panel's native resolution. How we've seen this implemented in many cases is with titles finally running at native resolution on the iPad 4 vs. some lower, scaled resolution on the iPad 3.
The Egypt Classic test is a much lighter workload, as a result most of these devices hit 60 fps at their native resolution:
Although Egypt HD is a bit overkill for today's games, Classic undershoots by a good amount. The offscreen test however does provide some guidance as to whether or not these devices would be able to hit 30 fps on an appreciably heavier workload:
Facebook
Twitter
RSS
113 Comments
View All Comments
Henk Poley - Wednesday, December 12, 2012 - link
I've been thinking about getting a black and a white tablet. One for serious stuff, and one for play.Pessimism - Friday, December 7, 2012 - link
I would like to see a direct comparison review between the ipad, nexus 10, and some of the generic chinese competition with similar specs such as the zenithink c94BSMonitor - Friday, December 7, 2012 - link
Is there an App that will let me confirm which version I have of the iPad 2?? Just recently purchased during the Black Friday fury on these, so assuming the 32nm one. ThanksZink - Friday, December 7, 2012 - link
http://www.anandtech.com/show/5789/the-ipad-24-rev...Scroll down, there are free ways to do it.
Dman23 - Friday, December 7, 2012 - link
Another great, comprehensive article from AnandTech! Well down Anand!!! :DMidwayman - Friday, December 7, 2012 - link
I wish there was a PDF rendering benchmark. From what I've been able to grasp its a very CPU dependent task, but it doesn't seem to correlate well to the java benchmarks that are typically used in cpu performance tests for tablets. For example many people say the ipad line does pretty poorly here despite the good standings in the java tests. I know I'm not the only one looking at tablets as a way to view large PDF tech docs, books, etc.bogieworf - Friday, December 7, 2012 - link
My biggest issue with the iPad is that it isn't trying to be more. The advances in the 4 would inspire few with the 3 to upgrade. Contrast this with the MS Surface. The device may be successful or it may not, but at the very least, MS has attempted to re-think aspects of the tablet. Then there the Lenovo yoga 11. Again, it may not succeed (actually I have my doubts on this one), but at least Lenovo is trying out new ideas in the tablet area. Just feels like a company like Apple with its past of groundbreaking designs should be trying to do more.darkcrayon - Friday, December 7, 2012 - link
The advances and the timing of the 4 were clearly not meant to inspire "3" users to upgrade. It was just a refresh to keep it up to date with the latest SoC tech to stay near the top in performance. And notice MS put much lower end hardware in the Surface than the iPad. Tegra 3? Low resolution screen? Low resolution camera?The 5th generation iPad will surely have an updated physical design - it should be a bit lighter and have an enclosure like the mini's. But there is little wrong with the iPad's hardware, if anything the more interesting pieces will be what they will do with the software.
bogieworf - Saturday, December 8, 2012 - link
I'm looking at the big picture. The touch type cover is innovative. The integrated kick stand is a neat feature. The automatically updating Tiles in Windows 8 is a neat feature. I'm talking innovation, not just a better camera or better processor.Maybe iPad 5 will feature new innovations, maybe not. Only time will tell. But there are other companies trying new things which I presently do not see with Apple.
iCrunch - Friday, December 7, 2012 - link
Thank you. Another great review. Love the attention to every last spec!You mentioned that you couldn't find a whole lot of examples where the iPad 4's both CPU and GPU performance increases are actually noticeable, except, of course, for gaming. I have found one other area where the difference is quite evident: VNC/RDP. The iPad 4 feels several orders of magnitude faster than the iPad 3, as opposed to "just 2x". Especially when you want to remotely control your Mac at High settings, as I do! Where the iPad 3 lagged, the iPad 4 is buttery smooth. As a result, everything is more accurate when you're "VNC'ing", you make fewer mistakes, and this obviously results in a much faster and less frustrating (or more fun, whichever you prefer) experience. (I use iTeleport, btw)
As a self-proclaimed power user, everything from loading webpages (thanks to 2x2 MIMO WiFi) to downloading apps to everyday mundane tasks are noticeably faster to me.